opengear-project / GEAR
GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
☆157Updated 8 months ago
Alternatives and similar repositories for GEAR:
Users that are interested in GEAR are comparing it to the libraries listed below
- ☆231Updated 10 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆279Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆81Updated this week
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 8 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆110Updated 3 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆336Updated 7 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆259Updated 4 months ago
- ☆116Updated last month
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- ☆52Updated 11 months ago
- ☆47Updated 3 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆89Updated last month
- A sparse attention kernel supporting mix sparse patterns☆164Updated last month
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆59Updated last week
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆59Updated 8 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆87Updated this week
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆47Updated 11 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆241Updated this week
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆202Updated last year
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆234Updated last month
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆121Updated last month
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆240Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆164Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 3 months ago
- ☆42Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- ☆145Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆99Updated 3 months ago